FADE: Towards Fairness-aware Augmentation for Domain Generalization via Classifier-Guided Score-based Diffusion Models

2024-06-13

AI Summary

Addressing the Fair Domain Generalization (FairDG) challenge—where fairness and generalization under distribution shifts are difficult to reconcile—this paper proposes FADE, a classifier-guided score-based diffusion model. Unlike conventional methods relying on strong disentanglement assumptions, FADE is the first to integrate score-based diffusion into FairDG, leveraging dual classifiers to collaboratively guide counterfactual data generation while explicitly decoupling sensitive attributes during sampling—thus jointly enforcing fairness constraints and distributional robustness. Its key innovations are: (1) generative fairness enhancement via explicit, rather than implicit, disentanglement; (2) a classifier-guided reverse sampling mechanism enabling controllable generation under fairness constraints; and (3) downstream training driven by generated data. Evaluated on three real-world datasets, FADE reduces average equalized odds (EQOP) gap by 37%, simultaneously improving both accuracy and fairness, and significantly outperforms existing state-of-the-art methods.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Ethics, Bias, and Fairness
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Fairness-aware domain generalization (FairDG) has emerged as a critical challenge for deploying trustworthy AI systems, particularly in scenarios involving distribution shifts. Traditional methods for addressing fairness have failed in domain generalization due to their lack of consideration for distribution shifts. Although disentanglement has been used to tackle FairDG, it is limited by its strong assumptions. To overcome these limitations, we propose Fairness-aware Classifier-Guided Score-based Diffusion Models (FADE) as a novel approach to effectively address the FairDG issue. Specifically, we first pre-train a score-based diffusion model (SDM) and two classifiers to equip the model with strong generalization capabilities across different domains. Then, we guide the SDM using these pre-trained classifiers to effectively eliminate sensitive information from the generated data. Finally, the generated fair data is used to train downstream classifiers, ensuring robust performance under new data distributions. Extensive experiments on three real-world datasets demonstrate that FADE not only enhances fairness but also improves accuracy in the presence of distribution shifts. Additionally, FADE outperforms existing methods in achieving the best accuracy-fairness trade-offs.

Problem

• Fairness
• Data Distribution Shift
• Fair Domain Generalization

Innovation

• FADE
• FairDG
• EnhancedGeneralization